Kurt Lieber

Cybersecurity Professional. Linux Enthusiast. World traveler.

[Kurt Lieber @klieber]

Haystack is a music discovery app that learns your taste from how your music sounds, not from its tags or likes. It has a server-side (docker) discovery service and a client-side ratings app that work together to do a better job of finding new music that you love.

https://t.co/upeG9cb5la

[Kurt Lieber @klieber]

A discovery engine is only as good as its feedback loop. haystack does not guess whether you liked a recommendation. It watches what you actually do.

Every hour, the sync job checks your Spotify plays, likes, and verdicts from its companion frontend, needle.

Like a track on Spotify or approve it in needle? That acoustic profile reinforces future positive matches.

If a liked track is missing from your local filesystem, haystack automatically routes it to a "To Rip" playlist so you know to acquire a permanent copy.

Leave a track unliked by the time next Monday's batch runs? Silence counts as a rejection. haystack logs the negative outcome, clears the slate, and sharpens the next batch.

https://t.co/upeG9cbDaI

[Eric S. Raymond @esrtweet]

Heads up, @OpenAI and @AnthropicAI. Rumor reaches my ears that you're doing a stupid thing, and should stop before you damage yourselves.

I hear you've now nerfed your models so that when people try to use them to clean the spamware and spyware out of their televisions, you block that.

If you really want Chinese open-weight models and open-source projects like OpenWaldo to eat your lunch, crippling your models so that people paying expensive subscriptions can't use them for completely legitimate purposes is a great way to accomplish this.

If, on the other hand, you'd rather have a volume business, maybe stupid arbitrary restrictions that look like they have the sole purpose of protecting corporate sleazeballs aren't such a good idea.

A word to the wise should be sufficient.

[Kurt Lieber @klieber]

@Ionkosm A model that competes with the frontier models

[Kurt Lieber @klieber]

@Umesh__digital Linux is a better OS, but damn Apple has some nice hardware. Looking forward to Omarchy getting their OS running on the M4 Pro chip soon!

[Kurt Lieber @klieber]

@ChanleeMunger I need to double check the code. I'm pretty sure that only happens after two weeks, but good to clarify either way.

Appreciate the feedback.

[Kurt Lieber @klieber]

How do you find a needle in a haystack without getting trapped in an algorithmic echo chamber?

Every morning at 05:00, haystack pulls candidate tracks from ListenBrainz and Deezer. It streams 30-second previews directly into memory, pipes them through ffmpeg, and generates audio embeddings on the fly. Nothing touches the disk, and rate limits stay strictly polite at one request every 1.1 seconds.

Scoring is mathematical and transparent:

Candidates are ranked by their closest acoustic match to music you already love.

They take a direct score penalty if they sound too close to tracks you have previously rejected.

Every Monday at 08:00, the top 15 tracks drop into your Spotify Discoveries playlist (capped at one track per artist, with 20% of the slots reserved for mid-score exploration).

https://t.co/upeG9cbDaI

[Kurt Lieber @klieber]

@dev_bre It's complete...until you run across the next cool plugin or theme. 😁

[Kurt Lieber @klieber]

@satya5n21 Happy to connect. I'm into linux (omarchy) and cybersecurity both.

[Kurt Lieber @klieber]

@bdsams Downloaded - I like it! It's essentially a harness for your harnesses and I love the ability to orchestrate across different agents and models. Will spend some time this weekend digging in more to learn it more effectively.

[Kurt Lieber @klieber]

@ardent__dev I haven't found anything that can compete on the same level as Opus 5.5. I have no allegiance to Anthropic or any other company, but as long as Opus remains king, I'll continue to use it.

[Kurt Lieber @klieber]

@Taniyatweets_ Anything with GNOME as the default DE.

[Kurt Lieber @klieber]

@tahasdx Looks awesome!

[Kurt Lieber @klieber]

@coryalthoff imo your results benefit the most from your ability to take a large, ambiguous problem and break it into small, manageable tasks, even with an AI assisting you. There's a lot of overlap there with "how smart someone is", but I do think the skill sets are separate.

[Kurt Lieber @klieber]

@JoshuaSWarren Incredible work! Thank you!

[Kurt Lieber @klieber]

@parkerbrowndev My biggest beef is it's hyprland-specific, so I can't use it on my work Mac, but I realize that's an architectural limitation given the way Gliff works.

But within its lane, it's unparalleled imo.

[Kurt Lieber @klieber]

@kamilbaranek_ Congrats! I'm building a music discovery service that fingerprints the songs you listen to and then finds more like it.
https://t.co/HuKaRkU1hj

[Kurt Lieber @klieber]

Haystack is a music discovery app that learns your taste from how your music sounds, not from its tags or likes. It has a server-side (docker) discovery service and a client-side ratings app that work together to do a better job of finding new music that you love.

https://t.co/upeG9cb5la

[Kurt Lieber @klieber]

Most music recommendation engines rely on collaborative filtering and messy genre tags. They recommend songs because strangers with overlapping playlists clicked like, not because the track actually fits what you want to hear.

I built haystack to fix this. It is a self-hosted music discovery engine for a single Spotify account running on an always-on Linux box.

Instead of trusting metadata, haystack learns your taste from the raw audio itself. It runs every track in your local library and your liked Spotify songs through Essentia's Discogs-EffNet model, analyzing up to nine 30-second windows per track. It maps how your music actually sounds, scouts new candidates, and builds a weekly Discoveries playlist.

https://t.co/upeG9cbDaI

[Kurt Lieber @klieber]

@W4HO_ Nice! I've got an old Pixel Pro 9 XL - maybe I'll throw this on there.

[Kurt Lieber @klieber]

@konig0000 > Perl